Yann Chevaleyre

I am Full Professor in computer science at Dauphine PSL, researcher in Artificial Intelligence.

News

• Research positions. 1 PhD and 1 postdoc position on robustness in AI

Research Interests

• Machine Learning
• Reinforcement Learning and Imitation in Robotics
• Game Theory, Multiagent Systems and Computational Social Choice

Current Teaching Activities

• Advanced Topics in Machine Learning, M2 IASD
• Introduction to Machine Learning, M1 I2D

Short Bio

• since 2024: responsible of the Data Science team in Lamsade with Khalid Belhajjame
• since 2017 : Full professor at LAMSADE, university of Paris Dauphine
• 2010 : Full professor at LIPN, head of the machine learning team
• 2002 : Assistant Professor at LAMSADE.
• 2001 : PhD in machine learning at LIP6

A Few Recent Publications

• Lucas Gnecco Heredia, Matteo Sammut, Muni Sreenivas Pydi, Rafael Pinot, benjamin negrevergne, Yann Chevaleyre, Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory (AISTATS 2025)

• Léo Dana, Muni Sreenivas Pydi, Yann Chevaleyre, Memorization in Attention-only Transformers (AISTATS 2025)

• Alexandre Verine, Muni Sreenivas Pydi, Benjamin Negrevergne, Yann Chevaleyre, Optimal Budgeted Rejection Sampling for Generative Models (AISTATS 2024)

• Florian Le Bronnec, Alexandre Verine, Benjamin Negrevergne, Yann Chevaleyre, Alexandre Allauzen Exploring Precision and Recall to assess the quality and diversity of LLMs (ACL 2024)

• Alexandre Verine, benjamin negrevergne, Muni Sreenivas Pydi, Yann Chevaleyre, Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows (Neurips 2023).

• Lucas Gnecco Heredia, Muni Sreenivas Pydi, Laurent Meunier, benjamin negrevergne, Yann Chevaleyre, On the Role of Randomization in Adversarially Robust Classification (Spotlight at Neurips 2023).

• Ikko Yamane, Yann Chevaleyre, Takashi Ishida, and Florian Yger, Mediated Uncoupled Learning and Validation with Bregman Divergences: Loss Family with Maximal Generality (AISTATS 2023)

• Laurent Meunier, Raphaël Ettedgui, Rafael Pinot, Yann Chevaleyre, Jamal Atif, Towards Consistency in Adversarial Classification (Neurips 2022).

• Geovani Rizk, Igor Colin, Albert Thomas, Rida Laraki, Yann Chevaleyre, An α-No-Regret Algorithm For Graphical Bilinear Bandits (Neurips 2022)

• Alexandre Verine, Benjamin Negrevergne, Fabrice Rossi, Yann Chevaleyre, On the expressivity of Normalizing Flows (ACML 2022)

• Rafael Pinot, Laurent Meunier, Florian Yger, Cédric Gouy-Pailler, Yann Chevaleyre, Jamal Atif, On the robustness of randomized classifiers to adversarial examples. Machine Learning Journal 111(9): 3425-3457 (2022)

• Alexis Duburcq, Guilhem Boéris, Nicolas Bredèche, Yann Chevaleyre, Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante. (IROS 2022)

• G. Rizk, A. Thomas, I. Colin, R. Laraki, Y. Chevaleyre, Best Arm Identification in Graphical Bilinear Bandits, International Conference on Machine Learning (ICML 2021)

• L. Meunier, M. Scetbon, R. Pinot, J. Atif, Y. Chevaleyre, Mixed Nash Equilibria in the Adversarial Examples Game, International Conference on Machine Learning (ICML 2021)

• A. Verine, B. Negrevergne, F. Rossi, Y. Chevaleyre On the expressivity of bi-Lipschitz normalizing flows, ICML Workshop on Invertible Neural Nets and Normalizing Flows (INNF 2021)

• L. Meunier, I. Legheraba, Y. Chevaleyre and O. Teytaud, Asymptotic convergence rates for averaging strategies, Foundations of Genetic Algorithms (FOGA 2021)

• A. Araujo, B. Negrevergne, Y. Chevaleyre, J. Atif, On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory, 35th Conference on Artificial Intelligence (AAAI 2021)

• R. Pinot, R. Ettedgui, G. Rizk, Y. Chevaleyre, J. Atif, Randomization matters How to defend against strong adversarial attacks, International Conference on Machine Learning (ICML 2020).

• L. Meunier, Y. Chevaleyre, J. Rapin, C. Royer, O. Teytaud, On Averaging the Best Samples in Evolutionary Computation. (PPSN 2020). pp.661-674

• A. Duburcq, Y. Chevaleyre, N. Bredeche, G. Boéris, Online trajectory planning through combined trajectory optimization and function approximation: Application to the exoskeleton Atalante. IEEE International Conference on Robotics and Automation (ICRA 2020), 3756-3762. Nominated for the Best Paper Award in Service Robotics.

• Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre and Jamal Atif. Understanding and Training Deep Diagonal Circulant Neural Networks 24th European Conference on Artificial Intelligence (ECAI 2020)

• K. Belahcene, N. Sokolovska, Y. Chevaleyre, J.-D. Zucker. Learning Interpretable Models using Soft Integrity Constraints, ACML 2020.

• M. Clertant, N. Sokolovska, Y. Chevaleyre, B. Hanczar, Interpretable Cascade Classifiers with Abstention (AISTATS 2019)

For more Publications, see google scholar or DBLP

Current PhD supervision

• Khunao Zheng, working on Automatic Test Generation for Code Execution with LLMs, at META, co-supervised with Benjamin Negrevergne
• Lucas Gnecco, working on Improved Defenses against Adversarial Attacks with Mixtures of Classifiers, co-supervised with Benjamin Negrevergne.
• Alexandre Vérine, working on Expressivity of Normalizing Flows, co-supervised with Benjamin Negrevergne and Fabrice Rossi.
• Louis-Henri Fernandez, working on Deep Learning for Physics applied to Maxwell Equations, at ST-Microelectronics.

Recent past PhD supervision

• Geovani Rizk, working on Graphical Bandits, co-supervised with Rida Laraki. (CIFRE with Huawei)
• Raphael Ettedgui, working on Game Theory and Adversarial Attacks co-supervised with Jamal Atif and Rafael Pinot
• Alexis Duburcq, working on Machine Learning and Reinforcement Learning for Exoskeleton trajectory optimization. (CIFRE with WanderCraft).

Contact Information

• e-mail: yann.chevaleyre (at) dauphine.fr
• postal address: Université Dauphine - PSL, Laboratoire LAMSADE, Place du Maréchal de Lattre de Tassigny, 75 775 Paris Cedex 16, France.